Abstract: Recognition of people by means of their biometric features is very popular among the society. There are a variety of biometric techniques including fingerprint recognition, face recognition and eye detection that are used for the privacy and safety purposes in different applications. In current years there has been an increasing interest in the learning of sparse representation of signals. Using an over completeglossary that contains prototype signal-atoms, signals are illustrated by sparse linear combinations of these atoms. Among several biometric recognition technologies, fingerprint compression is very popular for personal identification. One more fingerprint compression algorithm based on sparse representation is introduced. In the algorithm, first we construct a dictionary for predefined fingerprint photocopy patches. For a new given fingerprint images, suggest its patches according to the dictionary by computing l^0-minimization by MP method and then quantize and encode the representation. This paper compares dissimilar compression standards like JPEG, JPEG-2000, WSQ, K-SVDetc.The experiments demonstrate that this is often cost-effective compared with many competitive compression techniques particularly at high compression ratios.

Keywords: Fingerprint Compression, JPEG, JPEG 2000, WSQ, SPIHT, K-SVD, PSNR.